Categorical data: analyze and visualize

R For SAS Users

Melinda Higgins, PhD

Research Professor/Senior Biostatistician Emory University

Collapse categories

# Use table() inside with() for bmicat
daviskeep %>% with(table(bmicat))

bmicat
1. underwt/norm       2. overwt        3. obese
            161              35               3

Add recoded variable bmigt25

# Add one more categorical variable bmigt25
daviskeep <- daviskeep %>%
  mutate(bmigt25 = ifelse(bmi > 25,
                          "2. overwt/obese",
                          "1. underwt/norm"))

# View frequencies for bmigt25 categories
daviskeep %>% with(table(bmigt25))

bmigt25
1. underwt/norm 2. overwt/obese
            161              38

Contingency tables SAS and R

sas proc freq and r table function and crosstable from gmodels package

Chi-square tests SAS and R

sas proc freq and r codes for chisq.test and gmodels package crosstable function options

Contingency table and chi-square test

# Save table output of bmigt25 by sex
tablebmisex <- daviskeep %>%
  with(table(bmigt25, sex))
tablebmisex

# Use table object to run chisq.test
chisq.test(tablebmisex)

                 sex
bmigt25             F   M
  1. underwt/norm 107  54
  2. overwt/obese   4  34

Pearson's Chi-squared test with Yates'
continuity correction

data:  tablebmisex
X-squared = 36.759, df = 1, p-value = 1.336e-09

Chi-square tests with gmodels package

# Load gmodel package
library(gmodels)

# Run gmodels::CrossTabs, show column %s and expected values
daviskeep %>%
  with(gmodels::CrossTable(bmigt25, sex,
                           chisq = TRUE,
                           prop.r = FALSE,
                           prop.t = FALSE,
                           prop.chisq = FALSE,
                           expected = TRUE))

CrossTable output - part 1

   Cell Contents
|-------------------------|
|                       N |
|              Expected N |
|           N / Col Total |
|-------------------------|

Total Observations in Table:  199

                | sex
        bmigt25 |         F |         M | Row Total |
----------------|-----------|-----------|-----------|
1. underwt/norm |       107 |        54 |       161 |
                |    89.804 |    71.196 |           |
                |     0.964 |     0.614 |           |
----------------|-----------|-----------|-----------|
2. overwt/obese |         4 |        34 |        38 |
                |    21.196 |    16.804 |           |
                |     0.036 |     0.386 |           |
----------------|-----------|-----------|-----------|
   Column Total |       111 |        88 |       199 |
                |     0.558 |     0.442 |           |
----------------|-----------|-----------|-----------|

CrossTable output - part 2

gmodels::CrossTable() output - continued...

Statistics for All Table Factors

Pearson's Chi-squared test
------------------------------------------------------------
Chi^2 =  38.99402     d.f. =  1     p =  4.251066e-10

Pearson's Chi-squared test with Yates' continuity correction
------------------------------------------------------------
Chi^2 =  36.75936     d.f. =  1     p =  1.336475e-09

Mosaic plots SAS and R

sas proc freq freqplot option for tables statement and r mosaicplot function

Mosaicplot of two-way categorical proportions

# Make mosaicplot of bmigt25 by sex
mosaicplot(bmigt25 ~ sex,
           data = daviskeep,
           color = c("light blue",
                     "dark grey"),
           main =
             "BMI Categories by Sex")

mosaicplot of bmigt25 and sex of daviskeep dataset

Let's explore categorical associations for the abalones!

R For SAS Users